Image Segmentation for Object Modeling

1. A computer implemented method, comprising: accessing a set of images within a video stream; identifying an object of interest in one or more images of the set of images, the object of interest having a first portion and a second portion; detecting a region of interest within the one or more images; generating one or more binarization matrices from the one or more images; determining a pixel radius; filter the one or more binarization matrices to exchange a first pixel value for a second pixel value where a pixel associated with the first pixel value is proximate to a set of pixels of the second pixel value, based on the pixel radius; identifying a first thickness and a first set of median pixels of the first portion and a second thickness and a second set of median pixels of the second portion; determining a polyline approximating the first portion and the second portion of the object of interest; and generating a model for the polyline.

2. The method of claim 1 , wherein identifying the first set of median pixels for the first portion and the second set of median pixels for the second portion further comprises: identifying a first set of median pixels for the first portion of the object of interest, the first set of median pixels being a median pixel in each column, of the one or more binarization matrices, having a pixel associated with the first portion of the object of interest; identifying a second set of median pixels for the second portion of the object of interest, the second set of median pixels being a median pixel in each column, of the one or more binarization matrices, having a pixel associated with the second portion of the object of interest; and isolating the first set of median pixels and the second set of median pixels within the one or more binarization matrices from the remaining pixels.

3. The method of claim 2 , wherein determining the polyline further comprises: determining a bend position between the first portion and the second portion of the object of interest; determining a first line extending in a first direction from the bend position, the first line extending across one or more of the first set of median pixels; and determining a second line extending in a second direction from the bend position, the second line extending across one or more of the second set of median pixels.

4. The method of claim 3 , wherein generating the model for the polyline further comprises: determining a length for the first line and the second line; determining a bend angle for the bend position; and determining a slope angle for the first portion of the object of interest.

5. The method of claim 1 , wherein generating the model for the polyline further comprises: generating an averaged model based on a model generated for each image of the set of images of the video stream.

6. A system, comprising: one or more processors; and a non-transitory processor-readable storage medium storing processor executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising: accessing a set of images within a video stream; identifying an object of interest in one or more images of the set of images, the object of interest having a first portion and a second portion; detecting a region of interest within the one or more images; generating one or more binarization matrices from the one or more images; determining a pixel radius; filter the one or more binarization matrices to exchange a first pixel value for a second pixel value where a pixel associated with the first pixel value is proximate to a set of pixels of the second pixel value, based on the pixel radius; identifying a first thickness and a first set of median pixels of the first portion and a second thickness and a second set of median pixels of the second portion; determining a polyline approximating the first portion and the second portion of the object of interest; and generating a model for the polyline.

7. The system of claim 6 , wherein identifying the first set of median pixels for the first portion and the second set of median pixels for the second portion further comprises: identifying a first set of median pixels for the first portion of the object of interest, the first set of median pixels being a median pixel in each column, of the one or more binarization matrices, having a pixel associated with the first portion of the object of interest; identifying a second set of median pixels for the second portion of the object of interest, the second set of median pixels being a median pixel in each column, of the one or more binarization matrices, having a pixel associated with the second portion of the object of interest; and isolating the first set of median pixels and the second set of median pixels within the one or more binarization matrices from the remaining pixels.

8. The system of claim 7 , wherein determining the polyline further comprises: determining a bend position between the first portion and the second portion of the object of interest; determining a first line extending in a first direction from the bend position, the first line extending across one or more of the first set of median pixels; and determining a second line extending in a second direction from the bend position, the second line extending across one or more of the second set of median pixels.

9. The system of claim 8 , wherein generating the model for the polyline further comprises: determining a length for the first line and the second line; determining a bend angle for the bend position; and determining a slope angle for the first portion of the object of interest.

10. The system of claim 6 , wherein generating the model for the polyline further comprises: generating an averaged model based on a model generated for each image of the set of images of the video stream.

11. A non-transitory processor-readable storage medium storing processor executable instructions that, when executed by a processor of a machine, cause the machine to perform operations comprising: accessing a set of images within a video stream; identifying an object of interest in one or more images of the set of images, the object of interest having a first portion and a second portion; detecting a region of interest within the one or more images; generating one or more binarization matrices from the one or more images; determining a pixel radius; filter the one or more binarization matrices to exchange a first pixel value for a second pixel value where a pixel associated with the first pixel value is proximate to a set of pixels of the second pixel value, based on the pixel radius; identifying a first thickness and a first set of median pixels of the first portion and a second thickness and a second set of median pixels of the second portion; determining a polyline approximating the first portion and the second portion of the object of interest; and generating a model for the polyline.

12. The non-transitory processor-readable storage medium of claim 11 , wherein identifying the first set of median pixels for the first portion and the second set of median pixels for the second portion further comprises: identifying a first set of median pixels for the first portion of the object of interest, the first set of median pixels being a median pixel in each column, of the one or more binarization matrices, having a pixel associated with the first portion of the object of interest; identifying a second set of median pixels for the second portion of the object of interest, the second set of median pixels being a median pixel in each column, of the one or more binarization matrices, having a pixel associated with the second portion of the object of interest; and isolating the first set of median pixels and the second set of median pixels within the one or more binarization matrices from the remaining pixels.

13. The non-transitory processor-readable storage medium of claim 12 , wherein determining the polyline further comprises: determining a bend position between the first portion and the second portion of the object of interest; determining a first line extending in a first direction from the bend position, the first line extending across one or more of the first set of median pixels; and determining a second line extending in a second direction from the bend position, the second line extending across one or more of the second set of median pixels.

14. The non-transitory processor-readable storage medium of claim 13 , wherein generating the model for the polyline further comprises: determining a length for the first line and the second line; determining a bend angle for the bend position; and determining a slope angle for the first portion of the object of interest.

15. The non-transitory processor-readable storage medium of claim 11 , wherein generating the model for the polyline further comprises: generating an averaged model based on a model generated for each image of the set of images of the video stream.